Smart agriculture: real-time classification of green coffee beans by using a convolutional neural network

作     者：Huang, Nen-Fu Chou, Dong-Lin Lee, Chia-An Wu, Feng-Ping Chuang, An-Chi Chen, Yi-Hsien Tsai, Yin-Chun 

作者机构：Natl Tsing Hua Univ Dept Comp Sci Hsinchu Taiwan 

出 版 物：《IET SMART CITIES》 (IET Smart Cities)

年 卷 期：2020年第2卷第4期

页      面：167-172页

核心收录：

基　　金：Ministry of Science and Technology (MOST) of Taiwan [MOST 107-2218-E-007-004] 

主　　题：quality control image classification learning (artificial intelligence) beverages crops feature extraction agriculture convolutional neural nets real-time classification green coffee beans convolutional neural network economic crop coffee quality unpleasant beans labour-intensive manual selection speciality coffee products automatic coffee bean picking system coffee bean recognition rate smart agriculture image processing data augmentation technologies deep learning 

摘      要：Coffee is an important economic crop and one of the most popular beverages worldwide. The rise of speciality coffees has changed people s standards regarding coffee quality. However, green coffee beans are often mixed with impurities and unpleasant beans. Therefore, this study aimed to solve the problem of time-consuming and labour-intensive manual selection of coffee beans for speciality coffee products. The second objective of the authors study was to develop an automatic coffee bean picking system. They first used image processing and data augmentation technologies to deal with the data. They then used deep learning of the convolutional neural network to analyse the image information. Finally, they applied the training model to connect an IP camera for recognition. They successfully divided good and bad beans. The false-positive rate was 0.1007, and the overall coffee bean recognition rate was 93%.